MetaMCP Details
MetaMCP is a MCP proxy that lets you dynamically aggregate MCP servers into a unified MCP server, and apply middlewares. MetaMCP itself is a MCP server so it can be easily plugged into ANY MCP clients. It functions as an MCP Aggregator, Orchestrator, Middleware, and Gateway all in one docker image, enabling scalable, configurable hosting of multiple MCP servers behind a single endpoint with flexible authentication, tooling, and annotations. This README introduces core concepts such as MCP Server configurations, Namespaces, Endpoints, Middleware, Inspector, and Tool Overrides & Annotations, and provides quick-start guidance for running MetaMCP with Docker, building a development environment, and integrating with clients like Claude Desktop via proxies. It also covers MCP protocol compatibility, authentication options (including API keys, OAuth, and OIDC), and integration guidance for developers looking to remix MCP tool flows and middleware pipelines.
Use Case
MetaMCP serves as infrastructure to host dynamically composed MCP servers behind a unified endpoint. It enables grouping MCP servers into namespaces, hosting them as a meta-MCP, applying middlewares, and optionally overriding tool metadata per namespace. This is useful for organizations wanting to aggregate tools, prompts, and resources from multiple MCP servers, then expose a single endpoint with configurable authentication (API keys or OAuth) and transport options (SSE or Streamable HTTP). Example usage includes configuring a MetaMCP endpoint that aggregates multiple underlying MCP servers, then calling tools across those servers via the aggregated interface. See code examples for mcp.json configuration and client integrations (Claude Desktop and others) to illustrate how to connect and use the proxy. For example, a simple mcp.json to point to a MetaMCP endpoint looks like:
{
"mcpServers": {
"MetaMCP": {
"url": "http://localhost:12008/metamcp/<YOUR_ENDPOINT_NAME>/sse"
}
}
}To connect Claude Desktop or other stdio clients, you can proxy the remote MCP endpoint with mcp-proxy as shown in the docs:
Using Streamable HTTP
{
"mcpServers": {
"MetaMCP": {
"command": "uvx",
"args": [\
"mcp-proxy",\
"--transport",\
"streamablehttp",\
"http://localhost:12008/metamcp/<YOUR_ENDPOINT_NAME>/mcp"\
],
"env": {
"API_ACCESS_TOKEN": "<YOUR_API_KEY_HERE>"
}
}
}
}Using SSE
{
"mcpServers": {
"ehn": {
"command": "uvx",
"args": [\
"mcp-proxy",\
"http://localhost:12008/metamcp/<YOUR_ENDPOINT_NAME>/sse"\
],
"env": {
"API_ACCESS_TOKEN": "<YOUR_API_KEY_HERE>"
}
}
}
}Local development guidance also includes steps to install dependencies and run the project locally via pnpm, and Docker-based quick-start instructions for running the full stack in production.
Available Tools (4)
Examples & Tutorials
Code examples directly from the documentation:
MCP JSON example for a single STDIO MCP server:
"HackerNews": {
"type": "STDIO",
"command": "uvx",
"args": ["mcp-hn"]
}Example mcp.json for Cursor via MetaMCP endpoint (E.g., SSE):
{
"mcpServers": {
"MetaMCP": {
"url": "http://localhost:12008/metamcp/<YOUR_ENDPOINT_NAME>/sse"
}
}
}Claude Desktop integration (Using Streamable HTTP):
{
"mcpServers": {
"MetaMCP": {
"command": "uvx",
"args": [\
"mcp-proxy",\
"--transport",\
"streamablehttp",\
"http://localhost:12008/metamcp/<YOUR_ENDPOINT_NAME>/mcp"\
],
"env": {
"API_ACCESS_TOKEN": "<YOUR_API_KEY_HERE>"
}
}
}
}Claude Desktop integration (Using SSE):
{
"mcpServers": {
"ehn": {
"command": "uvx",
"args": [\
"mcp-proxy",\
"http://localhost:12008/metamcp/<YOUR_ENDPOINT_NAME>/sse"\
],
"env": {
"API_ACCESS_TOKEN": "<YOUR_API_KEY_HERE>"
}
}
}
}Installation Guide
Step-by-step installation instructions from the documentation:
1) Clone the repository
git clone https://github.com/metatool-ai/metamcp.git2) Enter the repository and prepare environment
cd metamcp
cp example.env .env3) Start with Docker Compose (production/deployment)
docker compose up -d4) For local development with development container or native setup, install dependencies and start the dev server
pnpm install
pnpm dev5) If you modify APP_URL env vars, ensure you only access from the APP_URL due to CORS policy
<h1 class="text-2xl font-semibold mt-5 mb-3">See docker-compose.yml for details on volumes and services</h1>Integration Guides
Frequently Asked Questions
Is this your MCP?
Claim ownership and get verified badge
Warnings and important notes from the docs:
Prerequisites before using MetaMCP:
Compare Alternatives
Similar MCP Tools
6 related toolsAnki MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application. The Anki MCP Server allows AI models to access Anki's card data, enabling features like automated flashcard creation, review, and management.
1MCP Agent
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one. The 1mcp-app/agent is an open-source project that provides a single entry point for multiple MCP servers, making it easier to manage and interact with various AI models and tools.
Roundtable AI MCP Server
Roundtable AI MCP Server is a zero-configuration local MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and a standardized interface. It coordinates specialized sub-agents from within your IDE to solve engineering problems in parallel, sharing context and synthesizing responses into a single, high-quality output. This documentation details installation, available MCP tools, integration with popular IDEs, and a broad ecosystem of specialized tools and CLIs that can be invoked as part of a roundtable-powered workflow, enabling developers to delegate tasks to the right AI for each facet of a problem without leaving their development environment.
MCPJungle
MCPJungle is a self-hosted MCP Gateway and Registry for AI agents. It serves as a central registry and gateway to manage Model Context Protocol (MCP) servers and the tools they expose. By consolidating MCP server registration, tool discovery, and access control, MCPJungle enables AI agents and clients to discover, group, and securely invoke tools from a single, unified gateway. The project provides a CLI, Docker-based deployment options, and enterprise-ready features such as tool grouping, access control, and observability to streamline MCP-based workflows across organizations.
mcpmcp-server
mcpmcp-server is a focused solution for discovering, setting up, and integrating MCP servers with your favorite clients to unlock AI-powered workflows. It streamlines how you connect MCP-powered servers to popular clients, enabling seamless AI-assisted interactions across your daily tools. The project emphasizes an approachable, config-driven approach to linking MCP servers with clients like Claude Desktop, while directing you to the homepage for variations across apps and platforms. This README highlights a practical JSON configuration example and notes on supported environments, helping you get started quickly and confidently.
Imagen3-MCP
Imagen3-MCP is an image generation service based on Google's Imagen 3.0 that exposes its functionality through MCP (Model Control Protocol). The project provides a server to run a local MCP service that accesses Google Gemini-powered image generation, enabling developers to integrate advanced image synthesis into their applications. The documentation covers prerequisites (Gemini API key), installation steps for Cherry Studio, and a Cursor-based JSON configuration example for embedding the MCP server in broader tooling. This MCP is designed to be deployment-friendly, with configurable environment variables and optional proxy settings to adapt to various network environments.